Skip to content
conftrace_

Surin Ahn

3 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ICLR (1) ICML (1) NeurIPS (1)

Top co-authors

Yuqing Yang (3) Lili Qiu (3) Yucheng Li (3) Qianhui Wu (3) Dongsheng Li (3) Xufang Luo (3) Amir H. Abdi (3) Huiqiang Jiang (3) Chengruidong Zhang (3) Jianfeng Gao (2)

Research topics

Machine Learning (3) Application Areas (3) Artificial Intelligence (2) Core AI (2) Deep Learning (1) Natural Language Processing (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Resources & Methods (1) Techniques (1)

Keywords

sparse attention (2) inference optimization (2) long context (2) inference acceleration (1) key-value cache (1) prompt compression (1) visual language model (1) large language model (1) gpu kernel (1) dynamic sparsity (1) prefilling stage (1) grid pattern (1) attention mechanism (1) pre-filling (1) efficient computing (1) memory efficiency (1)

Papers

MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention ICML 2025 SCBench: A KV Cache-Centric Analysis of Long-Context Methods ICLR 2025 MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention NeurIPS 2024